Fast-Vollib: A Fast Implied Volatility Library for Pythonwith PyTorch, JAX, and CUDA Fused-Kernel Backends

TL;DR

fast-vollib is an open-source Python library offering high-performance European option pricing, implied volatility computation, and Greeks, utilizing PyTorch, JAX, and CUDA for batched workloads and GPU acceleration.

Contribution

It introduces a pluggable, GPU-accelerated, fully-vectorized implied volatility library with a compatible API as a drop-in replacement for existing packages.

Findings

Achieves high-performance batched IV computations using CUDA and Triton kernels.

Provides a fully-vectorized implementation of Jäckel's LBR algorithm.

Offers a compatible API with existing Python option pricing libraries.

Abstract

We present fast-vollib, an open-source Python library that provides high-performance European option pricing, implied volatility (IV) computation, and Greeks under the Black-76, Black-Scholes, and Black-Scholes-Merton models. The library is designed as a drop-in alternative to the de-facto-standard py_vollib and py_vollib_vectorized packages, with pluggable PyTorch and JAX execution backends, a CUDA fused-kernel Triton contribution for batched IV workloads, and a compatibility-first public API. In addition to a vectorized Halley-method IV solver, fast-vollib ships an experimental, fully-vectorized implementation of J\"ackel's "Let's Be Rational" (LBR) algorithm with NumPy/Numba, torch.compile, JAX, and Triton single-pass GPU kernels for batched option chains. This note announces the library and describes its public API surface, with source, documentation, and packaging artifacts available at: GitHub (https://github.com/raeidsaqur/fast-vollib), Docs (https://raeidsaqur.github.io/fast-vollib/), PyPI (https://pypi.org/project/fast-vollib/).